Query-by-example spoken term detection for OOV terms

C Parada, A Sethy… - 2009 IEEE Workshop on …, 2009 - ieeexplore.ieee.org
The goal of spoken term detection (STD) technology is to allow open vocabulary search over
large collections of speech content. In this paper, we address cases where search term (s) of …

ASR error detection using recurrent neural network language model and complementary ASR

YC Tam, Y Lei, J Zheng, W Wang - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Detecting automatic speech recognition (ASR) errors can play an important role for effective
human-computer spoken dialogue system, as recognition errors can hinder accurate system …

[PDF][PDF] Contextual information improves OOV detection in speech

C Parada, M Dredze, D Filimonov… - … Technologies: The 2010 …, 2010 - aclanthology.org
Abstract Out-of-vocabulary (OOV) words represent an important source of error in large
vocabulary continuous speech recognition (LVCSR) systems. These words cause …

[PDF][PDF] A spoken term detection framework for recovering out-of-vocabulary words using the web

C Parada, A Sethy, M Dredze, F Jelinek - Paragraph, 2010 - isca-archive.org
Vocabulary restrictions in large vocabulary continuous speech recognition (LVCSR) systems
mean that out-of-vocabulary (OOV) words are lost in the output. However, OOV words tend …

Learning out-of-vocabulary words in automatic speech recognition

L Qin - 2013 - search.proquest.com
Abstract Out-of-vocabulary (OOV) words are unknown words that appear in the testing
speech but not in the recognition vocabulary. They are usually important content words such …

[PDF][PDF] Subword and phonetic search for detecting out-of-vocabulary keywords

D Karakos, R Schwartz - Fifteenth Annual Conference of the …, 2014 - isca-archive.org
We compare several approaches, separately and together, for spotting of out-of-vocabulary
(OOV) keywords, in terms of their ATWV scores. We considered three types of recognition …

ASR error segment localization for spoken recovery strategy

F Béchet, B Favre - 2013 IEEE International Conference on …, 2013 - ieeexplore.ieee.org
Even though small ASR errors might not impact downstream processes that make use of the
transcript, larger error segments like those generated by OOVs can have a considerable …

[PDF][PDF] OOV sensitive named-entity recognition in speech

C Parada, M Dredze, F Jelinek - Twelfth Annual Conference of the …, 2011 - isca-archive.org
Abstract Named Entity Recognition (NER), an information extraction task, is typically applied
to spoken documents by cascading a large vocabulary continuous speech recognizer …

[PDF][PDF] Towards using hybrid word and fragment units for vocabulary independent LVCSR systems

A Rastrow, A Sethy, B Ramabhadran… - … Annual Conference of …, 2009 - isca-archive.org
This paper presents the advantages of augmenting a word-based system with sub-word
units as a step towards building open vocabulary speech recognition systems. We show that …

Out-of-vocabulary word recovery using fst-based subword unit clustering in a hybrid asr system

E Egorova, L Burget - 2018 IEEE International Conference on …, 2018 - ieeexplore.ieee.org
The paper presents a new approach to extracting useful information from out-of-vocabulary
(OOV) speech regions in ASR system output. The system makes use of a hybrid decoding …